Oh Jaebeom PRO

EricJaebeom's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 2 days ago

FFHQ

Collection

Flickr-Faces-HQ (FFHQ) is a high-quality image dataset of human faces, originally created as a benchmark for image generation. • 5 items • Updated Jul 11 • 1

upvoted a collection 3 months ago

TIPSv2

Collection

TIPSv2 foundational vision-language models. Webpage: https://gdm-tipsv2.github.io/ • 9 items • Updated Jul 21 • 46

upvoted 2 papers 6 months ago

Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss

Paper • 2410.17243 • Published Oct 22, 2024 • 93

Efficient Universal Perception Encoder

Paper • 2603.22387 • Published Mar 23 • 11

upvoted 2 collections 6 months ago

EUPE

Collection

6 items • Updated Mar 30 • 29

SigLino: Vision Foundation Models (SigLIP2 + DINOv3)

Collection

Vision encoders distilled from DINOv3 and SigLIP2 (MoE & Dense). CVPR 2026. • 6 items • Updated Aug 13 • 17

upvoted a collection about 1 year ago

DINOv3

Collection

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 15 items • Updated Mar 10 • 824